CV / YOLO26

YOLO26n-seg

YOLO26n-seg performs instance segmentation with 80 COCO classes through HailoRT inference, outputting bounding boxes and instance masks.

Size

6.0 MB

Memory

4GB+

Precision

Hailo HEF / HailoRT

Choose the device you're using, the set up guide and documentation will update accordingly.

Platform

Inference Engine

Getting Started

Deploy

sudo docker run --rm \
  --name pi5-hailo-yolo26n-seg \
  --privileged \
  --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro 
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/yolo26n_seg:latest \
  python web_detection.py --model_path model/yolo26n_seg.hef --video_path video/test.mp4

REST API

Use the REST API to run inference. Copy the commands below.

Curl

curl -X POST "http://<Board_IP>:8000/api/models/yolo26n_seg/predict" \
  -F "file=@test.jpg"

Python

import requests
resp = requests.post(
    "http://<Board_IP>:8000/api/models/yolo26n_seg/predict",
    files={"file": open("test.jpg", "rb")},
    timeout=30,
)
print(resp.json())

Model Details

YOLO26n-seg on reComputer CM5 + Hailo-10H

YOLO26n-seg instance segmentation (2.7M params, COCO 80 classes), running on Hailo-10H via HailoRT.

Model Info

Property	Value
Architecture	YOLO26n-seg
Task	Instance Segmentation
Input	640×640×3 RGB
Output	Bounding boxes + instance masks
Parameters	2.7M
Source	Hailo Model Zoo

Hardware and Host Setup

Item	Value
Board	Raspberry CM5
Accelerator	Hailo-10H, `/dev/hailo0`
OS	Raspberry Pi OS Bookworm, aarch64

bash

sudo apt update && sudo apt install hailo-h10-all -y
sudo reboot

Run

bash

sudo docker run --rm --privileged --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/yolo26n_seg:latest \
  python web_detection.py --model_path model/yolo26n_seg.hef --video_path video/test.mp4

HEF Files

HEF	Size	Notes
`yolo26n_seg.hef`	6.0 MB	Instance segmentation model

REST API

bash

curl -X POST "http://<Board_IP>:8000/api/models/yolo26n_seg/predict" \
  -F "file=@test.jpg"

Endpoint	Method	Purpose
`/api/models/yolo26n_seg/predict`	POST	Boxes + masks (JSON)
`/api/models/yolo26n_seg/visualize`	POST	Detection overlay (JPEG)
`/api/models/yolo26n_seg/classes`	GET	COCO class list

Development

Source: src/hailo10h_yolo26n_seg/
Dockerfile: docker/hailo10h/yolo26n_seg.dockerfile

Inputs and Outputs

Input: image (640x640 RGB). Output: bounding boxes + instance masks (COCO 80 classes).